KR101669622B1 - Method and apparatus of the optimization-based path planning for autonomous navigation of unmanned ground vehicle - Google Patents

Method and apparatus of the optimization-based path planning for autonomous navigation of unmanned ground vehicle Download PDF

Info

Publication number
KR101669622B1
KR101669622B1 KR1020150100594A KR20150100594A KR101669622B1 KR 101669622 B1 KR101669622 B1 KR 101669622B1 KR 1020150100594 A KR1020150100594 A KR 1020150100594A KR 20150100594 A KR20150100594 A KR 20150100594A KR 101669622 B1 KR101669622 B1 KR 101669622B1
Authority
KR
South Korea
Prior art keywords
vehicle
unmanned
optimization
control input
state information
Prior art date
Application number
KR1020150100594A
Other languages
Korean (ko)
Inventor
신종호
이영일
김종희
이정석
주상현
Original Assignee
국방과학연구소
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 국방과학연구소 filed Critical 국방과학연구소
Priority to KR1020150100594A priority Critical patent/KR101669622B1/en
Application granted granted Critical
Publication of KR101669622B1 publication Critical patent/KR101669622B1/en

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0217—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with energy consumption, time reduction or distance reduction criteria
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D2201/0213—

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Feedback Control In General (AREA)

Abstract

The present invention relates to an optimization-based path planning method and apparatus for an autonomous running of an unmanned traveling vehicle that is capable of searching an optimized path by reflecting a kinematic model, dynamic characteristics, and environment recognition results of the unmanned traveling vehicle.
The optimization-based path planning method for an autonomous running of an unmanned traveling vehicle according to the present invention includes an initial control input generating step (S110) for generating a plurality of control inputs based on a current state of an unmanned traveling vehicle, (S120) for predicting future state information based on a kinematic model for each of the plurality of control inputs generated in the step (S120), and a step of estimating a future state information of the unmanned traveling vehicle satisfying the dynamic characteristics of the unmanned traveling vehicle (J) of the unmanned vehicle based on the future state information, the dynamic characteristics of the unmanned traveling vehicle, and the environment recognition result measured from the sensors installed in the vehicle, (S140) of determining an optimum condition satisfying an optimization condition (S 140); and an optimum condition satisfaction determination step S 150), and an optimum path generating step (S160) of calculating an optimal path of the unmanned vehicle using the control input satisfying the optimization condition.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to an optimization-based path planning method and apparatus for autonomous driving of an unmanned traveling vehicle,

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method and an apparatus for planning a route of an unmanned vehicle, and more particularly, The present invention relates to an optimization-based path planning method and apparatus for autonomous navigation of a vehicle.

An unmanned traveling vehicle that travels by controlling the driving means, the braking means, and the steering means by analyzing information acquired from a sensor installed in the vehicle without being ridden by the driver is placed in an environment where the unmanned traveling vehicle dynamically changes as it travels.

The unmanned traveling vehicle grasps the current position of the vehicle using a GPS (Global Positioning System) installed in the vehicle, and plans a traveling route based on the environment recognition result using information obtained from a laser sensor, a vision sensor, and the like.

In general, the environmental recognition result conveys the area that can be traveled to the unmanned vehicle, so the result of the environmental recognition becomes a constraint in the path planning. In addition, even if it is judged that the vehicle is able to travel, it is not possible that the unmanned vehicle can go to all of the unmanned vehicle, so that the kinematic characteristic and dynamic characteristic of the unmanned vehicle are additionally constrained.

The path planning of the unmanned traveling vehicle according to the related art plans a path by selecting a candidate path that can run among the predefined candidate paths.

However, it is not a simple matter to generate the candidate route in advance, and the type of the candidate route may be increased infinitely depending on the state in which the vehicle is located.

In addition, since the path of the unmanned vehicle is determined by selecting one of the predefined candidate paths, it is necessary to sufficiently reflect the state of the unmanned vehicle when generating the candidate path.

In addition, it is not easy to reflect the state of the unmanned traveling vehicle in a scheme of selecting a route after generating a candidate route in advance.

On the other hand, the following prior art documents disclose a technique relating to 'an automobile unmanned operation device and method'.

KR 10-0513065 B1

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and it is an object of the present invention to provide a vehicle navigation system capable of searching an optimized route by considering a state of an unmanned vehicle reflecting kinematic models and dynamic characteristics, The present invention provides an optimization-based route planning method and apparatus for autonomous navigation of an unmanned traveling vehicle.

According to another aspect of the present invention, there is provided an optimization-based path planning method for an autonomous running of an unmanned traveling vehicle, the method including: generating an initial control input based on a current state of the unmanned traveling vehicle; A future state information prediction step of predicting future state information based on a kinematic model for each of the plurality of control inputs generated in the initial control input generation step; And determining a cost function of the unmanned vehicle based on the future state information, the dynamic characteristics of the unmanned traveling vehicle, and the environment recognition result measured from the sensors installed in the vehicle, , An optimal condition satisfying a plurality of cost functions obtained in the optimization step to determine whether the optimization condition is satisfied And single step, and a best path generating step of calculating the optimal path of the unmanned vehicle to the control input that satisfies the optimization condition.

In the future state information prediction step, the future state information of the vehicle is predicted by the following equation.

Figure 112015068642275-pat00001
,
Figure 112015068642275-pat00002
,
Figure 112015068642275-pat00003

(only,

Figure 112015068642275-pat00004
: X-axis velocity component of unmanned vehicle,
Figure 112015068642275-pat00005
: Y-axis velocity component of the unmanned vehicle, V: linear velocity of the unmanned vehicle, ψ: heading angle of the unmanned vehicle,
Figure 112015068642275-pat00006
: Change rate of heading angle of unmanned vehicle, r: control input)

Wherein the optimization is performed by applying a Particle Swarm Optimization (PSO) algorithm.

In the optimization step, optimization is performed using the following equation.

Figure 112015068642275-pat00007

(Where J k +1 : current cost function, J k : Previous cost function, ε: reference value)

In the optimum condition satisfaction determination step, the optimal control input satisfying the following equation is determined.

Figure 112015068642275-pat00008

(Where J k +1 : current cost function, J k : Previous cost function, ε: reference value)

Meanwhile, an optimization-based path planning apparatus for an autonomous running of an unmanned traveling vehicle according to the present invention includes an initial control input generating unit for generating a plurality of control inputs necessary for predicting a position and a path of an unmanned vehicle utilizing a kinematic model, A vehicle state predicting unit for predicting future state information of the unmanned driving vehicle as a control input generated by the initial control input generating unit, a dynamic characteristic examining unit for checking whether the future state information satisfies the dynamic characteristics of the unmanned driving vehicle, Calculating a cost function of the unmanned vehicle based on the future state information, the dynamic characteristics, and the environment recognition result measured from the sensors installed in the vehicle installed in the unmanned vehicle, A path planning optimization unit for determining a control input to be determined by the path planning optimization unit, It applied to the kinematic model of the vehicle to the optimal path and includes a generator for generating an optimal path.

And the vehicle state predicting unit predicts future state information of the vehicle by the following equation.

Figure 112015068642275-pat00009
,
Figure 112015068642275-pat00010
,
Figure 112015068642275-pat00011

(only,

Figure 112015068642275-pat00012
: X-axis velocity component of unmanned vehicle,
Figure 112015068642275-pat00013
: Y-axis velocity component of the unmanned vehicle, V: linear velocity of the unmanned vehicle, ψ: heading angle of the unmanned vehicle,
Figure 112015068642275-pat00014
: Change rate of heading angle of unmanned vehicle, r: control input)

The path planning optimization unit may optimize a path by applying a Particle Swarm Optimization (PSO) algorithm.

The path planning optimization unit may be optimized using the following equation.

Figure 112015068642275-pat00015

(Where J k +1 : current cost function, J k : Previous cost function, ε: reference value)

The path planning optimization unit determines an optimum control input for determining an optimal condition in the following equation.

Figure 112015068642275-pat00016

(Where J k +1 : current cost function, J k : Previous cost function, ε: reference value)

According to the optimization-based route planning method and apparatus for an autonomous running of an unmanned traveling vehicle according to the present invention, a kinematic model and dynamic characteristics of the unmanned traveling vehicle are taken into consideration, and based on the environment recognition result obtained in the unmanned traveling vehicle, It is possible to search for an optimal route for the unmanned vehicle to reach the destination.

1 is a flowchart showing an optimization-based path planning method for an autonomous running of an unmanned traveling vehicle according to the present invention;
2 is a block diagram showing an optimization-based path planning apparatus for an autonomous running of an unmanned traveling vehicle according to the present invention.
FIG. 3 is a graph showing an optimal path selected according to the present invention; FIG.

Hereinafter, an optimization-based path planning method for an autonomous running of an unmanned traveling vehicle according to the present invention will be described in detail with reference to the accompanying drawings.

The optimization-based path planning method for an autonomous running of an unmanned traveling vehicle according to the present invention includes an initial control input generating step (S110) for generating a plurality of control inputs based on a current state of an unmanned traveling vehicle, (S120) for predicting future state information based on a kinematic model for each of the plurality of control inputs generated in the step (S120), and a step of estimating a future state information of the unmanned traveling vehicle satisfying the dynamic characteristics of the unmanned traveling vehicle (J) of the unmanned vehicle based on the future state information, the dynamic characteristics of the unmanned traveling vehicle, and the environment recognition result measured from the sensors installed in the vehicle, (S140) of determining an optimum condition satisfying an optimization condition (S 140); and an optimum condition satisfaction determination step S 150), and an optimum path generating step (S160) of calculating an optimal path of the unmanned vehicle using the control input satisfying the optimization condition.

In the initial control input generation step S110, an arbitrary control input (r i , i = 1, 2, ..., N) for selecting an optimal path of the unmanned traveling vehicle is generated. The earliest control inputs generate N arbitrary control inputs, but from the next step, the control input based on the PSO (Particle Swarm Optimization) is updated using the size of the cost function.

The future state information predicting step (S120) predicts future state information based on the kinematic model of the unmanned driving vehicle represented by the following equation according to the control input inputted in the initial control input generating step (S110).

Figure 112015068642275-pat00017
,
Figure 112015068642275-pat00018
,
Figure 112015068642275-pat00019

Here, x and y are the positions of the unmanned vehicle during running on the plane, V is the commanded speed command, and ψ is the heading angle of the unmanned vehicle.

Figure 112015068642275-pat00020
Is an x-axis velocity component,
Figure 112015068642275-pat00021
The y-axis velocity component,
Figure 112015068642275-pat00022
Represents a heading angle change rate, and r represents a control input, and the heading angle refers to the traveling direction of the unmanned vehicle traveling on the x, y plane.

Accordingly, the future state information prediction step (S120) predicts the future position and heading angle of the unmanned vehicle according to the control input inputted in the control input generating step (S110).

Meanwhile, the future state information predicted in the future state information prediction step S120 is generated by the number of control inputs input in the initial control input generation step S110. For example, if N initial control input values are input in the initial control input generation step S110, N future state information is predicted in the future state information prediction step S120.

The dynamic characteristic checking step S130 checks the dynamic characteristic that the future state information acquired in the future state information prediction step S120 should satisfy with the unmanned vehicle. For example, the dynamic characteristics that the unmanned vehicle must satisfy are the linear velocity of the unmanned vehicle

Figure 112015068642275-pat00023
,
Figure 112015068642275-pat00024
) And the control input r i . That is, a larger value is added to the cost function depending on the amount that exceeds the constraint.

The dynamic property thresholding step (S130) is a concept of checking the constraint condition of the dynamic property and integrating a value proportional to the size beyond the constraint condition into the cost function calculation.

If the unattended traveling vehicle satisfies the dynamic characteristics, optimization is performed using the cost function (S140). In the optimization step, the cost function (J) is defined as the following equation with the future state information, the dynamic characteristics of the unmanned vehicle, and the environment recognition result as constraints.

Figure 112015068642275-pat00025

Here, f (x, y) denotes an environment recognition result corresponding to the position when the unmanned vehicle is located at x i , y i , and r i denotes a control input , Which generates an optimal path that reflects the environment recognition result but does not use much control input.

Further, in the optimization step, optimization is performed by applying a PSO (Particle Swarm Optimization) algorithm.

Unlike other search algorithms, the PSO algorithm has advantages such as global optimization for large and complex functions like evolutionary algorithms, and is faster than evolutionary algorithms. .

Therefore, in the optimization step S140, it is possible to define a search for a control input (r i , i = 1, 2, ..., N) that minimizes the cost function J while satisfying the dynamic characteristics of the unmanned vehicle .

In the optimum condition satisfaction determination step S150, it is determined whether the condition performed in the optimization step S140 satisfies the optimization condition. The optimization condition determines whether the optimization result performed in the optimizing step S140 satisfies the following optimal condition.

Figure 112015068642275-pat00026

Here, epsilon is a predetermined constant, and k means the number of repetitions of optimization. That is, the beginning of the control input (r i, i = 1, 2, ..., N) for when the cost function value based on said J 1 utilizing J 1 because the J 0 control input (r i, i = 1, 2, ..., N). Then, the cost function J 2 is determined using the newly generated control input (r i , i = 1, 2, ..., N). In this way, the cost function J 1 , ... And J k , and determines that the optimum condition is satisfied if the absolute value of the difference between the current cost function J k + 1 and the previous cost function J k is less than a predetermined reference value ε.

If the control input (r i , i = 1, 2, ..., N) obtained from the optimization step (S140) in the optimum condition satisfaction step S150 satisfies the optimization condition, the control input at that time is stored in the unmanned vehicle The optimal path generation step (S160) for generating an optimal path is performed.

If the control input (r i , i = 1, 2, ..., N) obtained from the optimization step S140 does not satisfy the optimization condition in the optimal condition satisfaction determination step S150, The process returns to step S120 and the above-described process is repeated.

The optimal path obtained by the above-described series of processes can be represented by R in FIG. The area (A) indicated in blue is an area in which the unmanned traveling vehicle can travel, and the area (B) indicated in red is an area in which the unmanned traveling vehicle can not travel.

Hereinafter, an optimization-based path planning apparatus for an autonomous running of an unmanned traveling vehicle according to the present invention will be described with reference to FIG.

The optimization-based path planning apparatus for an autonomous running of an unmanned traveling vehicle according to the present invention is an apparatus for performing an optimization-based path planning method for autonomous traveling of an unmanned traveling vehicle as described above.

The optimization-based path planning apparatus 10 for an autonomous running of an unmanned traveling vehicle according to the present invention includes an initial control input generating unit 12 for generating a plurality of control inputs necessary for predicting a position and a path of an unmanned vehicle utilizing a kinematic model, (12) for predicting the future state information of the unmanned vehicle using the control input generated by the initial control input generator (11), and a controller Of the unmanned traveling vehicle based on the future state information, the dynamic characteristics, and the environment recognition result measured from the sensors installed in the vehicle installed in the unmanned traveling vehicle, A path planning optimization unit 14 for calculating a function J and determining a control input for minimizing the calculated cost function J; Applying a control input to the kinematic models of the unmanned vehicle to the optimal path and a generator 15 for generating an optimal path.

The initial control input generating unit 11 generates a control input necessary for predicting the position and path of the unmanned vehicle utilizing the kinematic model. Based on the current state of the vehicle, a plurality of control inputs (r i , i = 1, 2, ..., N) are generated.

The vehicle state predicting unit 12 predicts future state information of the unmanned vehicle using the control input generated by the initial control input generating unit 11. [ Predicts future state information based on a kinematic model for each control input for a plurality of control inputs (r i , i = 1, 2, ..., N) generated by the initial control input generating unit.

The dynamic characteristic investigating unit 13 examines the dynamic characteristic satisfaction of the unmanned vehicle with the predicted future state information from the vehicle state predicting unit 12. The dynamic characteristic investigation unit 13 checks whether the future state information satisfies the dynamic characteristic that the unmanned vehicle must satisfy.

The path planning optimization unit 14 generates a plurality of control inputs (r i , i = 1, 2, ...) for calculating an optimal path by using the future state information, the satisfaction of the dynamic characteristic and the environment recognition result as constraints. , N).

In the path plan optimization unit 14, optimization is performed using a PSO (Particle Swarm Optimization) algorithm for a plurality of control inputs. The path planning optimization unit 14 optimizes the future state information and the satisfaction of the dynamic characteristic according to the constraint to obtain a control input that minimizes the cost function J while satisfying the dynamic characteristics of the unmanned vehicle Find.

The optimum path generating unit 15 generates an optimal path by applying the optimal control input selected by the path planning optimizing unit 14 to the kinematic model of the unmanned vehicle.

10: Path Planning Apparatus 11: Initial Control Input Generator
12: vehicle condition predicting unit 13: dynamic characteristic examination unit
14: Path planning optimization unit 15: Optimum path generation unit
S110: initial control input generation step S120: prediction of future state information
S130: Dynamic property check step S140: Optimization step
S150: Determination of Optimum Condition Satisfaction Step S160: Optimum Path Creation Step

Claims (10)

An initial control input generation step of generating a plurality of control inputs based on a current state of the unmanned vehicle,
A future state information prediction step of predicting future state information based on a kinematic model for the plurality of control inputs generated in the initial control input generation step,
A dynamic characteristic checking step of checking whether the future state information of the unmanned traveling vehicle satisfies the dynamic characteristics of the unmanned traveling vehicle,
An optimization step of obtaining a cost function of the unmanned vehicle based on the future state information, the dynamic characteristics of the unmanned traveling vehicle, and the environment recognition result measured from the sensors installed in the vehicle,
An optimal condition satisfaction judging step of judging whether a plurality of cost functions obtained in the optimization step satisfy an optimization condition,
And an optimum path generating step of calculating an optimum path of the unmanned vehicle using the control input satisfying the optimization condition,
Wherein the future state information prediction step predicts the future state information of the vehicle according to the following equation.
Figure 112016055454127-pat00046
,
Figure 112016055454127-pat00047
,
Figure 112016055454127-pat00048

(only,
Figure 112016055454127-pat00049
: X-axis velocity component of unmanned vehicle,
Figure 112016055454127-pat00050
: Y-axis velocity component of the unmanned vehicle, V: linear velocity of the unmanned vehicle, ψ: heading angle of the unmanned vehicle,
Figure 112016055454127-pat00051
: Change rate of heading angle of unmanned vehicle, r: control input) delete The method according to claim 1,
Wherein the optimizing step is performed by applying a Particle Swarm Optimization (PSO) algorithm to optimize the path planning for the autonomous running of the unmanned traveling vehicle. The method of claim 3,
Wherein the optimization is performed using the following equation in the optimization step.
Figure 112015068642275-pat00033

(J k + 1 : current cost function, J k : previous cost function, ε: reference value) The method according to claim 1,
Wherein the optimal control input satisfying the following equation is determined in the optimum condition satisfaction determination step.
Figure 112015068642275-pat00034

(J k + 1 : current cost function, J k : previous cost function, ε: reference value) An initial control input generator for generating a plurality of control inputs necessary for predicting a position and a path of the unmanned vehicle utilizing a kinematic model,
A vehicle state predicting unit for predicting future state information of the unmanned vehicle using the control input generated by the initial control input generating unit;
A dynamic characteristic examination unit for examining whether the future state information satisfies the dynamic characteristics of the unmanned traveling vehicle,
Calculating a cost function of the unmanned vehicle based on the future state information, the dynamic characteristics, and the environment recognition result measured from the sensors installed in the vehicle installed in the unmanned vehicle, A path planning optimization unit for determining a control input to be performed,
And an optimal path generation unit for generating an optimum path by applying the control input determined by the path planning optimization unit to the kinematic model of the unmanned traveling vehicle,
Wherein the vehicle state predicting unit predicts future state information of the vehicle according to the following equation.
Figure 112016055454127-pat00052
,
Figure 112016055454127-pat00053
,
Figure 112016055454127-pat00054

(only,
Figure 112016055454127-pat00055
: X-axis velocity component of unmanned vehicle,
Figure 112016055454127-pat00056
: Y-axis velocity component of the unmanned vehicle, V: linear velocity of the unmanned vehicle, ψ: heading angle of the unmanned vehicle,
Figure 112016055454127-pat00057
: Change rate of heading angle of unmanned vehicle, r: control input) delete The method according to claim 6,
Wherein the path planning optimizer applies a Particle Swarm Optimization (PSO) algorithm to optimize the path. The optimizing-based path planning apparatus for an autonomous running of an unmanned traveling vehicle, 9. The method of claim 8,
Wherein the route planning optimization unit optimizes the route planning by using the following equation.
Figure 112015068642275-pat00041

(J k + 1 : current cost function, J k : previous cost function, ε: reference value) The method according to claim 6,
Wherein the path planning optimization unit determines an optimum control input for determining an optimum condition in the following equation.
Figure 112015068642275-pat00042

(Where J k +1 : current cost function, J k : Previous cost function, ε: reference value)


KR1020150100594A 2015-07-15 2015-07-15 Method and apparatus of the optimization-based path planning for autonomous navigation of unmanned ground vehicle KR101669622B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020150100594A KR101669622B1 (en) 2015-07-15 2015-07-15 Method and apparatus of the optimization-based path planning for autonomous navigation of unmanned ground vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020150100594A KR101669622B1 (en) 2015-07-15 2015-07-15 Method and apparatus of the optimization-based path planning for autonomous navigation of unmanned ground vehicle

Publications (1)

Publication Number Publication Date
KR101669622B1 true KR101669622B1 (en) 2016-10-26

Family

ID=57251706

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020150100594A KR101669622B1 (en) 2015-07-15 2015-07-15 Method and apparatus of the optimization-based path planning for autonomous navigation of unmanned ground vehicle

Country Status (1)

Country Link
KR (1) KR101669622B1 (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107992050A (en) * 2017-12-20 2018-05-04 广州汽车集团股份有限公司 Pilotless automobile local path motion planning method and device
KR20180126205A (en) 2017-05-17 2018-11-27 국방과학연구소 An autonomous augmented remote control method for unmanned ground vehicles
CN109668569A (en) * 2018-12-08 2019-04-23 华东交通大学 Path rapid generation in a kind of intelligent driving
CN110083149A (en) * 2018-01-26 2019-08-02 百度（美国）有限责任公司 For infeed mechanism after the path of automatic driving vehicle and speed-optimization
KR20190095622A (en) * 2018-01-26 2019-08-16 충북대학교 산학협력단 Method and Apparatus for Planning Obstacle Avoiding Path
CN111857112A (en) * 2019-04-12 2020-10-30 广州汽车集团股份有限公司 Automobile local path planning method and electronic equipment
CN116166061A (en) * 2023-04-26 2023-05-26 中国农业大学 Unmanned speed control method and device, unmanned plane and electronic equipment
CN118545097A (en) * 2024-07-30 2024-08-27 浙江摩坦科技有限公司 Automatic control method and system for unmanned vehicle

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100513065B1 (en) 1998-08-25 2005-11-11 주식회사 현대오토넷 Automobile unmanned driving device and method
KR101484514B1 (en) * 2013-06-17 2015-01-21 한국과학기술원 Method, system and server of stability guaranteeing model predictive control based on particle swarm optimization

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100513065B1 (en) 1998-08-25 2005-11-11 주식회사 현대오토넷 Automobile unmanned driving device and method
KR101484514B1 (en) * 2013-06-17 2015-01-21 한국과학기술원 Method, system and server of stability guaranteeing model predictive control based on particle swarm optimization

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20180126205A (en) 2017-05-17 2018-11-27 국방과학연구소 An autonomous augmented remote control method for unmanned ground vehicles
CN107992050A (en) * 2017-12-20 2018-05-04 广州汽车集团股份有限公司 Pilotless automobile local path motion planning method and device
CN107992050B (en) * 2017-12-20 2021-05-11 广州汽车集团股份有限公司 Method and device for planning local path motion of unmanned vehicle
CN110083149A (en) * 2018-01-26 2019-08-02 百度（美国）有限责任公司 For infeed mechanism after the path of automatic driving vehicle and speed-optimization
KR20190095622A (en) * 2018-01-26 2019-08-16 충북대학교 산학협력단 Method and Apparatus for Planning Obstacle Avoiding Path
KR102151811B1 (en) * 2018-01-26 2020-09-03 충북대학교 산학협력단 Method and Apparatus for Planning Obstacle Avoiding Path
CN110083149B (en) * 2018-01-26 2022-05-13 百度（美国）有限责任公司 Path and speed optimized feedback mechanism for autonomous vehicles
CN109668569A (en) * 2018-12-08 2019-04-23 华东交通大学 Path rapid generation in a kind of intelligent driving
CN111857112A (en) * 2019-04-12 2020-10-30 广州汽车集团股份有限公司 Automobile local path planning method and electronic equipment
CN111857112B (en) * 2019-04-12 2023-11-14 广州汽车集团股份有限公司 Automobile local path planning method and electronic equipment
CN116166061A (en) * 2023-04-26 2023-05-26 中国农业大学 Unmanned speed control method and device, unmanned plane and electronic equipment
CN118545097A (en) * 2024-07-30 2024-08-27 浙江摩坦科技有限公司 Automatic control method and system for unmanned vehicle

Similar Documents

Publication Publication Date Title
KR101669622B1 (en) Method and apparatus of the optimization-based path planning for autonomous navigation of unmanned ground vehicle
CN108445750B (en) Method and system for vehicle motion planning
CN111033422B (en) Drift correction between planning and control phases of operating an autonomous vehicle
US11661068B2 (en) Vehicle system for recognizing objects
JP6674019B2 (en) Control error correction planning method for operating autonomous vehicles
US10571916B2 (en) Control method for autonomous vehicles
US11269329B2 (en) Dynamic model with learning based localization correction system
US10613489B2 (en) Method and system for determining optimal coefficients of controllers for autonomous driving vehicles
US11055540B2 (en) Method for determining anchor boxes for training neural network object detection models for autonomous driving
US20200341474A1 (en) Method and device for generating an autonomous driving trajectory of a vehicle
CN111123906B (en) Optimal longitudinal trajectory generation under different lateral acceleration constraints
KR20180053142A (en) Apparatus for determining route of autonomous vehicle and method thereof
JP2020534202A (en) Context-specific tolerances for motion control in autonomous vehicles
US20200363816A1 (en) System and method for controlling autonomous vehicles
EP3868624B1 (en) Method and system for actuating a control substem of an autonomous driving vehicle
JP2005339241A (en) Model prediction controller, and vehicular recommended manipulated variable generating device
US11436498B2 (en) Neural architecture search system for generating a neural network architecture
WO2021189374A1 (en) A navigation route planning method for autonomous vehicles
US11673584B2 (en) Bayesian Global optimization-based parameter tuning for vehicle motion controllers
US10732632B2 (en) Method for generating a reference line by stitching multiple reference lines together using multiple threads
CN111240314B (en) Vehicle accelerator/brake assist system based on predetermined calibration table for L2 autopilot
JP2016143240A (en) Lane change optimization device and program
US20210200220A1 (en) Multi-layer grid based open space planner
CN112305911B (en) Feedback prediction control method and device under complex environment and vehicle
US20230415736A1 (en) Systems and methods for controlling longitudinal acceleration based on lateral objects

Legal Events

Date Code Title Description
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
FPAY Annual fee payment

Payment date: 20191002

Year of fee payment: 4